---
title: "Pranav's Dashboard"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: fill
    social: [ "twitter", "facebook", "menu"]
    source_code: embed
---

```{r setup, include=FALSE}
library(flexdashboard)
library(knitr)
library(DT)
library(rpivotTable)
library(ggplot2)
library(plotly)
library(dplyr)
library(openintro)
library(highcharter)
library(ggvis)
```


```{r}
data <- read.csv("/Users/pranavvinod/Downloads/airlinedata", header = T)
```

```{r}
mycolors <- c("blue", "#FFC125", "darkgreen", "darkorange")
```

Interactive Data Visualization
=====================================

Row
-------------------------------------

### Airline Delay Analysis

```{r}
valueBox(paste("Delay"),
         color = "warning")
```

### Total Arrival Delays in US(in mins)

```{r}
a<-data %>% 
  summarise(Count = sum(ArrDelay, na.rm=TRUE))
valueBox((a$Count),
         icon = "fa-user")
```

### **Delay in mins**

```{r}
gauge(round(mean(data$ArrDelayMinutes, na.rm = TRUE),
            digits = 2),
            min = 0,
            max = 60,
            gaugeSectors(success = c(0, 5),
                         warning = c(5, 15),
                         danger = c(15, 60),
                         colors = c("green", "yellow", "red")))
```

### Massachusetts

```{r}
b <- data %>% filter(OriginStateName=="Massachusetts") %>% 
  summarise(Sum = sum(ArrDelay, na.rm=TRUE)) %>% 
  arrange(desc(Sum))
valueBox((b$Sum),
         icon = 'fa-building')
```

### California

```{r}
b <- data %>% filter(OriginStateName=="California") %>% 
  summarise(Sum = sum(ArrDelay, na.rm=TRUE)) %>% 
  arrange(desc(Sum))
valueBox((b$Sum),
         icon = 'fa-building')
```

### Texas

```{r}
b <- data %>% filter(OriginStateName=="Texas") %>% 
  summarise(Sum = sum(ArrDelay, na.rm=TRUE)) %>% 
  arrange(desc(Sum))
valueBox((b$Sum),
         icon = 'fa-building')
```

### Florida

```{r}
b <- data %>% filter(OriginStateName=="Florida") %>% 
  summarise(Sum = sum(ArrDelay, na.rm=TRUE)) %>% 
  arrange(desc(Sum))
valueBox((b$Sum),
         icon = 'fa-building')
```

Row
-------------------------------

### Failures By State

```{r}
p1 <- data %>%
         group_by(OriginStateName) %>%
         summarise(count = n()) %>%
         plot_ly(x = ~OriginStateName,
                 y = ~count,
                  color = "blue", 
                  type = 'bar') %>% 
 layout(xaxis = list(title = "Departure Delays By State"), 
 yaxis = list(title = 'Count')) 
 p1 
``` 

### Top States

```{r}

# g4 <- data %>% group_by(DestStateName) %>% 
#   summarise(c = sum(ArrDelayMinutes, na.rm=TRUE)) %>% 
#   arrange(desc(c))
p2 <- data %>%
         group_by(DestStateName) %>%
         summarise(count = sum(ArrDelayMinutes, na.rm=TRUE)) %>%
         filter(count>12000) %>%
         plot_ly(labels = ~DestStateName,
                 values = ~count,
                 marker = list(colors = mycolors)) %>%
         add_pie(hole = 0.2) %>%
         layout(xaxis = list(zeroline = F,
                             showline = F,
                             showticklabels = F,
                             showgrid = F),
                yaxis = list(zeroline = F,
                             showline = F,
                             showticklabels=F,
                             showgrid=F))
p2
```


Row
------------------------------------
### Scatter Plot of Arrival Delay vs Departure Delay

```{r}
d <- data %>% filter(DepDelay >=0) %>%  
   filter(ArrDelay >= 0) 
p3 <- plot_ly(d, x=~DepDelay) %>%
         add_markers(y =~ArrDelay,
                     text = ~paste("Arrival Delay: ", ArrDelay),
                     showlegend = F) %>%
         add_lines(y = ~fitted(loess(ArrDelay ~ DepDelay)),
                   name = "Loess Smoother",
                   color = I("#FFC125"),
                   showlegend = T,
                   line = list(width=5)) %>%
         layout(xaxis = list(title = "Departure Delay"),
                yaxis = list(title = "Arrival Delay"))
p3
```

### Box Plot of Top State

```{r}
# data %>%
#          group_by(State) %>%
#          ggvis(~State, ~lc, fill = ~State) %>%
#          layer_boxplots()
d1 <- data %>% group_by(DestStateName) %>% 
  summarise(Count = n()) %>% 
  arrange(desc(Count))
d2 <- data %>% filter(DestStateName=="California"|DestStateName=="Texas"|DestStateName=="Illinois"|DestStateName=="Georgia"|DestStateName=="Florida")
d1 <- d2 %>% filter(ArrDelay<100, na.rm=TRUE)

#Transforming data to box plot data
d1 <-data_to_boxplot(d1,ArrDelay, DestStateName, group_var = DestStateName)

#Plotting
highchart() %>% 
  hc_xAxis(type="category") %>% 
  hc_add_series_list(d1) %>% 
  hc_title(text = "Arrival Delay in 5 Busiest Airports") %>% 
  hc_yAxis(title = list(text="Arrival Delay(mins)"))
  
```

Map
========================================

### Map

```{r}
states <- data %>% group_by(OriginStateName) %>% 
  summarise(Mean = mean(DepDelay,na.rm = TRUE))

highchart() %>% 
  hc_add_series_map(usgeojson, states,
                    name = "OriginStateName",
                    value = "Mean",
                    joinBy = c('woename', 'OriginStateName')) %>% #woename is where on earth name and joins
 hc_mapNavigation(enabled = T) %>% 
  hc_title(text = "US map with average departure delay in minutes")

```

Data Table
========================================

```{r}

datatable(data,
          caption = "Delay Data",
          rownames = T,
          filter = "top",
          options = list(pageLength = 25))
```

Carrier Comparision
========================================

```{r}

data %>% group_by(UniqueCarrier) %>% 
  summarise(Mean = mean(DepDelayMinutes,na.rm=TRUE)) %>% 
  hchart(type = "column", hcaes(x=UniqueCarrier,y=Mean)) %>% 
  hc_title(text = 'Mean Departure Delay per Carrier') %>% 
  hc_yAxis(title=list(text='Average Departure Delay(mins)'))

```

Delay Cause Analysis
=========================================

```{r}

c1 <- data %>% group_by(DayofMonth) %>% 
  summarise(Count = sum(CarrierDelay, na.rm = TRUE))
c2 <- data %>% group_by(DayofMonth) %>% 
  summarise(Count = sum(WeatherDelay, na.rm = TRUE))
c3 <- data %>% group_by(DayofMonth) %>% 
  summarise(Count = sum(NASDelay, na.rm = TRUE))
c4 <- data %>% group_by(DayofMonth) %>% 
  summarise(Count = sum(SecurityDelay, na.rm = TRUE))
c5 <- data %>% group_by(DayofMonth) %>% 
  summarise(Count = sum(LateAircraftDelay, na.rm = TRUE))

#Plotting multiple lines
ggplot(c1,aes(DayofMonth)) +
  geom_line(aes(y=c1$Count,colour = "Carrier Delay"))+
  geom_line(aes(y=c2$Count,colour='Weather Delay'))+
  geom_line(aes(y=c3$Count,colour='NAS Delay'))+
  geom_line(aes(y=c4$Count,colour='Security Delay'))+
  geom_line(aes(y=c5$Count,colour='Late Aircraft Delay')) +
  scale_color_manual("",
                     breaks = c("Carrier Delay","Weather Delay","NAS Delay","Security Delay","Late Aircraft Delay"),
                     values = c("purple","blue","green","yellow","red")) +
  ggtitle("Variation of Causes of Delay per day of month")+
  scale_x_continuous("Day of Month") +
  scale_y_continuous("Total delay in mins")  +
  theme_bw()
```

Summary {data-orientation=columns}
===========================================

Column
-----------------------------------

### Average Departure Delays in the Month

```{r}
x1 <- data %>% group_by(FlightDate) %>% 
  summarise(Mean = mean(DepDelayMinutes, na.rm=TRUE))
valueBox(round(mean(x1$Mean), digits =2),
         icon = "fa-user" )
```

### Average difference in estimated and actual flying time

```{r}
valueBox(round(mean(-data$AirTime + data$CRSElapsedTime, na.rm=TRUE),
               digits = 2),
         icon = "fa-area-chart")
```

### Average Arrival Delays in the Month

```{r}
x2 <- data %>% group_by(FlightDate) %>% 
  summarise(Mean = mean(ArrDelayMinutes, na.rm=TRUE))
valueBox(round(mean(x2$Mean), digits =2),
         icon = "fa-user" )
```

Column
---------------------------

Report

* This is a report on `r length(data$DepDelay)` airline delays.

* Average difference in estimated and actual flying time was 25.59 minutes.

* Average Departure Delays in the  Month was 10.5 minutes.

* Average Arrival Delays in the  Month was 11.28 minutes.

This report was generated on `r format(Sys.Date(), format = "%B %d, %Y")`.

About Report
========================================

Created by: Pranav Vinod 

Course: POM 681 - Business Analytics and Data Mining

University: University of Massachusetts, Dartmouth

Confidential: HIGHLY!